arXiv subjects

Yong Li

Publications and source records attributed to Yong Li.

At least 91 records · Page 5Linked to original sources

arXiv2026

From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents

Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference time. On-policy self-distillation (OPSD) offers a promising direction, but many existing methods typically supervise students by scoring actions along student-generated trajectories. Such supervision has two limitations: teacher preferences are not validated by environment outcomes, and action-level scores underuse information from student rollouts, teacher rollouts, and their behavioral relationship. We therefore advocate outcome-verified teacher supervision and comparative learning over teacher-student trajectories. Based on this view, we propose Outcome-Verified Comparative Self-Distillation (OVCSD). OVCSD organizes failed student rollouts into a prefix tree, adaptively invokes a skill-conditioned teacher from student-reached states, and retains only outcome-verified successful continuations. It then applies localized comparative learning at the first state-aligned divergence and distills the post-divergence teacher suffix to transfer completion behavior. Experiments on ALFWorld and WebShop across three model scales show that OVCSD consistently outperforms skill-free RL and existing self-distillation baselines, achieving up to 29.7 and 5.4 absolute success-rate gains over the strongest baselines on ALFWorld and WebShop, respectively, while adding less than 3% privileged interaction during training.

cs.AI↗

arXiv2026

Spatial Lifting for Dense Prediction

We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a higher-dimensional space and subsequently processing them using networks designed for that higher dimension, such as a 3D U-Net. Counterintuitively, this dimensionality lifting allows us to achieve good performance on benchmark tasks compared to conventional approaches, while reducing inference costs and \textbf{drastically lowering the number of model parameters}. The SL framework produces intrinsically structured outputs along the lifted dimension. This emergent structure facilitates dense supervision during training and enables single-forward-pass self-consistency-based quality and uncertainty estimation at test time. Spatial Lifting introduces a simple and general modeling strategy that offers a promising path toward more efficient, accurate, and reliable deep networks for dense prediction tasks in vision.

cs.CV↗

arXiv2026

Non-equilibrium fluctuations of a two-species exclusion process with slow boundary

We study the non-equilibrium density fluctuations of a one-dimensional two-species symmetric simple exclusion process in contact with critical slow boundary reservoirs. The boundary rates are of order $1/n$, which leads to Robin boundary conditions at the macroscopic level. We prove that the coupled fluctuation field associated with the empirical densities of two species converges to a generalized Ornstein-Uhlenbeck process. The limiting process is characterized by a linear martingale problem whose coefficients reflect the combined effects of bulk diffusion, species conversion, and the boundary reservoirs.

math.PR↗

arXiv2026

Latent Variable-Mediated Cross-Learning for Few-Shot Acoustic Impedance Imaging

Acoustic impedance imaging is a fundamental yet severely ill-posed problem in subsurface analysis: the seismic wavelet is unknown, observations are band-limited, and labeled well-log samples are extremely scarce (typically <1% of all traces). Existing semi-supervised deep learning methods mitigate few-shot problem by incorporating forward modeling, yet they either rely on inaccurate prior wavelet assumptions or introduce auxiliary networks, leading to unstable optimization and degraded performance. We propose RD-SCL, a novel framework that integrates regularized deconvolution with semi-supervised cross-learning. At its core lies a differentiable, closed-form first-order Tikhonov deconvolution operator that dynamically estimates the latent wavelet in the frequency domain during training, providing stable physics-guided feedback without explicit auxiliary networks and fixed wavelet priors. Building on this operator, we design a symmetric cross-learning that enforces consistency between predictions on labeled and unlabeled data, thereby effectively exploiting abundant unlabeled traces. Extensive experiments on the SEAM and Marmousi 2 benchmarks demonstrate that RD-SCL consistently outperforms state-of-the-art supervised and semi-supervised methods, achieving substantial gains with lower computational cost. With only 56.5k learnable parameters and competitive runtime, RD-SCL offers a practical, physically consistent, and efficient solution for acoustic impedance imaging.

cs.CV↗

arXiv2026

Entropy-Based Characterization of Fluctuations in Stochastically Perturbed Integrable Hamiltonian Systems

We study the entropy characteristics of stochastic fluctuations arising from randomly perturbed integrable Hamiltonian systems. Starting from action-angle dynamics, we derive a discrete fluctuation process and investigate its asymptotic randomness from both dynamical and information theoretic perspectives. On the dynamical side, we establish an entropy variational principle for the induced shift dynamics on an energy-constrained infinite-dimensional path space. We show that, among all invariant probability measures satisfying the asymptotic energy constraint inherent to the system, the maximal entropy rate is attained by a Gaussian product measure. This establishes an entropy variational principle for stochastic dynamical trajectories under an asymptotic energy constraint. On the statistical side, we characterize the asymptotic Gaussian behavior of accumulated fluctuations through information-theoretic convergence. Beyond weak convergence given by the central limit theorem, we prove convergence of relative entropy and total variation distance between the fluctuation distributions and their Gaussian limits.

math.DS↗

arXiv2026

Effective stability for Hamiltonian PDEs vanishing spectral gaps

This paper studies the effective stability of nearly integrable Hamiltonian PDEs with asymptotically vanishing spectral gaps ($0 < α< 1$). Under a unified high-low frequency decomposition, we construct a modified block clustering partition based on Bourgain's ideas. By leveraging the vanishing of spectral gaps to suppress high-frequency resonant contributions, the overall non-resonance property is maintained under high-regularity weights. This framework is applied to space fractional and fully dispersive Whitham-Schrödinger equations, uniformly yielding explicit stability estimates in Gevrey, logarithmic ultra-differentiable, and Sobolev spaces.

math.AP↗

arXiv2026

3D Geometric Tooth Alignment Planning via Deep Reinforcement Learning

3D geometric tooth alignment planning, which determines sequential trajectories from initial malocclusion to the final target alignment, is a cornerstone of modern digital orthodontics. This paper presents a novel deep reinforcement learning (DRL) framework to automate the generation of these alignment paths. We formulate the planning process as a Markov Decision Process (MDP) to capture its sequential decision-making nature, focusing on optimizing geometric trajectories while integrating essential spatial constraints, such as inter-dental collision avoidance and path efficiency. The proposed method leverages the Deep Deterministic Policy Gradient (DDPG) algorithm, enhanced by three key innovations: (1) a Transformer-based agent to model complex spatial interactions between teeth and manage high-dimensional state-action spaces; (2) a dynamic masking scheme that restricts movement to a sparse subset of teeth per step, better reflecting the clinical logic of sequential alignment; and (3) a two-stage curriculum learning strategy that gradually increases task difficulty to ensure training stability and efficient path discovery. We evaluate our approach on a dataset of 10K expert-designed treatment plans based on clinical data. Experimental results demonstrate that our method outperforms existing baselines in terms of path safety and geometric efficiency, providing a robust and automated solution for 3D geometric orthodontic alignment planning.

cs.CV↗

arXiv2026

AgentSociety 2: An Integrated Research Environment for Executable Social Science

AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or laboratory protocols, but integrated social processes involving situated participants, interaction contexts, interventions, and outcomes. Yet a critical link is missing: existing systems either assist isolated research tasks or simulate agents as experimental subjects, leaving the research workflow and simulated society decoupled. Here we introduce AgentSociety 2, an Integrated Research Environment for executable social science. It couples two roles of LLM agents in the same runtime: AI social scientists that coordinate literature grounding, hypothesis generation, experiment design, simulation execution, result interpretation, and manuscript drafting; and silicon participants that generate behavioral responses within configurable social environments. This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow. Across seven illustrative studies spanning micro-level social-science laboratory experiments, meso-level dynamics in social media, and macro-level urban scenarios, we demonstrate its capacity to support diverse disciplinary questions, reproduce major qualitative patterns from prior studies, identify informative deviations, and enable large-scale simulations through optimized agent-environment interactions. By preserving human researchers' high-level agency while delegating procedural orchestration to agentic systems, it provides a human-in-the-loop and controllable infrastructure for next-generation computational social science, with broader applications in scalable computational social experimentation and AI-enabled social governance platforms.

cs.CY↗

arXiv2026

Unidirectional Transverse Scattering in Acoustic Dimers

We study unidirectional transverse scattering in a two-dimensional acoustic dimer composed of two circular subwavelength scatterers. Using a coupled multipole model, we show that interparticle coupling enables effective monopole--dipole interference and supports a transverse Kerker effect under plane-wave excitation. In contrast to a single non-absorbing rotationally symmetric particle, where Kerker-type directional scattering is only approached in the weak-scattering limit, the dimer can combine pronounced directionality with strong overall scattering. This regime is promising for compact acoustic beam steering and directional wave routing.

physics.class-ph↗

arXiv2026

Onsager--Machlup Functionals for Generalized Newtonian Equations of Motion with Time-Varying Fractional Noise

In this paper, we derive the Onsager--Machlup functional for a class of degenerate stochastic differential equations on $\mathbb{R}^{m+n}$ driven by $n$-dimensional fractional Brownian motion with time-dependent diffusion coefficients, where the Hurst parameter satisfies $H\in(1/4,1)$. The main difficulty arises from the interaction between the degenerate structure and the multidimensional fractional noise, which produces nontrivial coupling terms under small-ball conditioning. By combining the Gaussian correlation inequality with an approximation argument for infinite-dimensional convex sets, we establish a decoupling mechanism that allows these coupling effects to be controlled by unconditional Gaussian expectations. Furthermore, through regularity estimates for the degenerate components and sharp Hölder norm estimates, we eliminate the remaining coupling contributions and obtain an explicit expression for the Onsager--Machlup functional. As applications of the derived functional, we obtain the corresponding constrained Euler--Lagrange equations characterizing the most probable transition paths of the system, and establish a sufficient condition under which the stochastic differential equation preserves the most probable path.

math.PR↗

arXiv2026

Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control

World models are rapidly becoming a core infrastructure for embodied intelligence and interactive agents: they provide controllable simulators in which agents can perceive, act, forecast, and acquire scalable experience. Yet current video generation world models are still organized around isolated control interfaces, such as camera trajectories, robot actions, or hand-joint signals. This fragmentation is increasingly a scaling bottleneck. The central challenge is not the absence of controllable generators, but the lack of a unified and extensible learning framework that can absorb heterogeneous action supervision while preserving a shared model of world dynamics. In this work, we introduce Worldscape-MoE, a Mixture-of-Experts world model built on Diffusion Transformers for scalable heterogeneous action control. Our key observation is that different controls specify different interfaces to the same underlying world: although their representations differ, they constrain shared physical regularities, scene dynamics, and interaction semantics. Worldscape-MoE operationalizes this observation through modality-aware control injection, shared and control-specific experts, and a progressive MoE tuning strategy that supports continual extension to new action modalities. Experiments across locomotion, robotic manipulation, and egocentric hand control show that heterogeneous supervision improves rather than interferes with individual control capabilities. Worldscape-MoE achieves strong results on WorldArena, improves locomotion and hand-control metrics, exhibits robust out-of-distribution generalization, and demonstrates scaling behavior as additional control data and experts are integrated.

cs.RO↗

arXiv2026

Linking effective Ratner equidistribution to the semicircle law for skew-shift matrices

We consider large Hermitian matrices whose entries are defined by evaluating the exponential function along orbits of the skew-shift $\frac{j(j-1)}{2}ω+ jy + x \mod 1$ for irrational $ω$. We establish a rigorous connection between the effective Ratner equidistribution theorem for unipotent orbits in $\SL(3,\R)/\SL(3,\Z)$ and the global semicircle law for such deterministic matrices. For frequency sequences satisfying a Diophantine condition, we prove that the empirical spectral distribution of these matrices converges to the Wigner semicircle law with optimal polynomial rate $O(N^{-1})$; for rectangular matrices the corresponding Marchenko--Pastur law is obtained. The proof uses a multi-parameter effective mixing property derived from the effective Ratner equidistribution theorem, combined with a graph-theoretic expansion of the moments. Our results evidence the quasirandom nature of the skew-shift dynamics observed in other contexts by Bourgain, Goldstein and Schlag, and Rudnick, Sarnak and Zaharescu, and provide a dynamical systems proof of the semicircle law with an improved convergence rate.

math.DS↗

arXiv2026

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose \textbf{RoadBench}, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using Bird's-Eye View (BEV) and First-Person View (FPV) image inputs. This benchmark comprises eight tasks consisting of 3,040 strictly manually verified test cases, constructed from 2,137 unique BEV images and 721 unique FPV images collected from five Chinese cities with relatively consistent traffic conventions. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 20 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs.

cs.CV↗

arXiv2026

Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents

Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. However, existing approaches predominantly rely on pre-defined agentic workflows. This constraint severely limits the flexibility required to navigate the vast search space of scientific literature and the complex action space of research reasoning. Recently, training Agentic LLMs has emerged as a promising direction, offering flexible reasoning frameworks and the capability for autonomous tool utilization. However, there remains a non-trivial challenge: applying previous agentic data synthesis methods to scientific ideation suffers from prohibitively high data synthesis cost. To bridge this gap, we propose Agentic-Ideation, a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation. Specifically, we first define a comprehensive tool space incorporating three external tools and three cognitive tools. Then we introduce an Oracle-Guided Data Synthesis strategy. By leveraging a reference idea as oracle guidance, this approach steers the multi-agent system to efficiently reconstruct the logical reasoning and tool invocation paths, transforming aimless trial-and-error into directed trajectory generation. Finally, we train the agent on these synthesized trajectories, employing a masking strategy on tool execution results. This ensures the model focuses on decision-making logic without interference from external feedback. Experimental results demonstrate that our method outperforms the SOTA workflow-based baseline by \textbf{11.91\%} in overall quality. Furthermore, our approach improves the sample efficiency of high-quality data synthesis by \textbf{over 10$\times$}.

cs.AI↗

arXiv2026

Kofola 1.0: A Modular Approach to ω-Regular Complementation and Inclusion Checking (Technical Report)

We present Kofola, an efficient tool for complementation and inclusion checking of Büchi automata, two central tasks in automata-theoretic verification with applications in model checking, monitoring, and theorem proving. Kofola implements a state-of-the-art modular complementation framework that decomposes the input automaton into strongly connected components and applies to each component a complementation algorithm tailored to its structural properties. Building on this modular construction, Kofola also provides modular inclusion checking with new heuristics. A key ingredient is a new on-the-fly emptiness-checking algorithm for the simple generalized Rabin pair condition produced by our complementation, allowing the search to terminate as soon as the explored state space suffices. Empirical evaluation shows that Kofola is highly competitive with state-of-the-art complementation and inclusion-checking tools: it is the most robust tool in our evaluation and often outperforms competitors by several orders of magnitude on benchmarks from practical applications.

cs.LO↗

arXiv2026

Complementing Emerson-Lei Elevator Automata (Technical Report)

Büchi elevator automata naturally appear in several areas of formal methods as a structural expressibly-equivalent subclass of Büchi automata where every strongly connected component is either deterministic or inherently weak. It was shown that this class contains the majority of Büchi automata generated in practical applications, including LTL model-checking and verification of hyperproperties. Moreover, the elevator subclass enables more efficient complementation and determinization algorithms than unrestricted Büchi automata. In this paper, we introduce Emerson-Lei elevator automata, which is a generalization of Büchi elevator automata to richer acceptance conditions. We provide a complementation algorithm with a significantly better asymptotic complexity than the best known algorithm for unrestricted Emerson-Lei automata. The practical efficiency of our algorithm is demonstrated by an experimental comparison with the popular state-of-the-art tool Spot. Our work is, to the best of our knowledge, the first step towards practical algorithms for complementing, determinizing, and testing universality and inclusion of Emerson-Lei automata with rich acceptance conditions.

cs.FL↗

arXiv2026

EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation

Estimating origin-destination (OD) flows under disruptive events is important for disaster response and urban resilience. Existing deep OD models trained on routine mobility often degrade when extreme events abruptly alter regional functions and population activities, while retraining a new generator for each event is impractical under limited event-time supervision. We propose EventOD, an event-adaptive OD generation framework that steers a pretrained OD generator using structured event semantics. EventOD first uses a large language model to infer region-level functional and demographic control vectors from coarse event observations. It then learns two lightweight adaptation modules, AlphaNet and BetaNet, to calibrate the magnitude of these semantic shifts, and further introduces a retrieval-augmented fallback pathway for scenarios with sparse supervision. The resulting event-conditioned features are injected into a pretrained graph diffusion OD model through input-level modulation, enabling event-aware adaptation without updating generator parameters. Experiments on hurricane- and pandemic-induced mobility across U.S. counties show that EventOD consistently improves both reconstruction accuracy and distributional fidelity over strong baselines. Source code is available at https://anonymous.4open.science/r/EventOD-5C11/.

cs.AI↗

arXiv2026

Picard-Lefschetz theory and alien calculus: a case study

We compare Picard--Lefschetz theory and resurgence in three basic one-dimensional exponential integrals: the Airy model, the Bessel model, and the Gamma model. On the Picard--Lefschetz side, we describe the Lefschetz thimbles and compute the connecting trajectories between critical points appearing at Stokes phases. On the resurgent side, we analyze the Borel singularities of the saddle expansions and use alien operators to recover the same Stokes coefficients. These examples serve as explicit finite-dimensional test cases for the dictionary between thimble wall-crossing and alien calculus.

math-ph↗